--other=fix script

projects/medical/2d_image/microscopy_images/2pm_vessel/README.md

@@ -63,6 +63,15 @@ export PYTHONPATH=`pwd`:$PYTHONPATH
 - run script `"python tools/prepare_dataset.py"` to format data and change folder structure as below.
 - run script `"python ../../tools/split_seg_dataset.py"` to split dataset and generate `train.txt`, `val.txt` and `test.txt`. If the label of official validation set and test set can't be obtained, we generate `train.txt` and `val.txt` from the training set randomly.
 
+```shell
+mkdir data & cd data
+pip install opendatalab
+odl get    2-PM_Vessel_Dataset
+cd ..
+python tools/prepare_dataset.py
+python tools/prepare_dataset.py
+```
+
 ```none
   mmsegmentation
   ├── mmseg

projects/medical/2d_image/microscopy_images/2pm_vessel/tools/prepare_dataset.py

@@ -5,7 +5,10 @@
 
 root_path = 'data/'
 
-src_dir = os.path.join(root_path, '2-PM_Vessel_Dataset')
+image_dir = os.path.join(root_path,
+                         '2-PM_Vessel_Dataset/raw/vesselNN_dataset/denoised')
+label_dir = os.path.join(root_path,
+                         '2-PM_Vessel_Dataset/raw/vesselNN_dataset/labels')
 tgt_img_train_dir = os.path.join(root_path, 'images/train/')
 tgt_mask_train_dir = os.path.join(root_path, 'masks/train/')
 os.system('mkdir -p ' + tgt_img_train_dir)
@@ -19,23 +22,25 @@ def filter_suffix(src_dir, suffix):
     return sorted(file_paths), sorted(file_names)
 
 
-path_list, _ = filter_suffix(src_dir, suffix='.tif')
-
-for path_label in path_list:
-    labels = tiff.imread(path_label)
-    assert labels.ndim == 3
-    path_image = path_label.replace('_label', '')
-    name = path_image.split('/')[-1].replace('.tif', '')
-    images = tiff.imread(path_image)
-    assert images.shape == labels.shape
-    # a single .tif file contains multiple slices
-    # as long as it is read by tifffile package.
-    for i in range(labels.shape[0]):
-        slice_name = name + '_' + str(i).rjust(3, '0') + '.png'
-        image = images[i]
-        label = labels[i] // 255
-
-        save_path_label = os.path.join(tgt_mask_train_dir, slice_name)
-        Image.fromarray(label).save(save_path_label)
-        save_path_image = os.path.join(tgt_img_train_dir, slice_name)
-        Image.fromarray(image).convert('RGB').save(save_path_image)
+if __name__ == '__main__':
+
+    image_path_list, _ = filter_suffix(image_dir, suffix='tif')
+    label_path_list, _ = filter_suffix(label_dir, suffix='.tif')
+
+    for img_path, label_path in zip(image_path_list, label_path_list):
+        labels = tiff.imread(label_path)
+        images = tiff.imread(img_path)
+        assert labels.ndim == 3
+        assert images.shape == labels.shape
+        name = img_path.split('/')[-1].replace('.tif', '')
+        # a single .tif file contains multiple slices
+        # as long as it is read by tifffile package.
+        for i in range(labels.shape[0]):
+            slice_name = name + '_' + str(i).rjust(3, '0') + '.png'
+            image = images[i]
+            label = labels[i] // 255
+
+            save_path_label = os.path.join(tgt_mask_train_dir, slice_name)
+            Image.fromarray(label).save(save_path_label)
+            save_path_image = os.path.join(tgt_img_train_dir, slice_name)
+            Image.fromarray(image).convert('RGB').save(save_path_image)